Commit Graph
2877 Commits
Author SHA1 Message Date
sam 19a6311f6c feat(telegram): /restart to reload config without dropping tasks (16.35)
Operator escape hatch: reload gateway config (notably the sender
allowlist) or recover a wedged adapter from chat, with no shell access to
the host.

Start becomes a supervisor loop that relaunches the bot on request, so a
restart is scoped to the gateway: the daemon keeps running and in-flight
agent tasks are untouched. Exiting the process would also have restarted
under the unless-stopped policy, but would have killed running work.

Two failure modes are handled deliberately:

- The handler runs on the very bot the supervisor is about to stop, so it
  hands off over a buffered channel and returns instead of tearing down
  inline, which would deadlock the restart it just requested. A duplicate
  request while one is in flight is dropped, not queued.
- A failed config reload logs and relaunches on the previous settings, so
  a bad config edit cannot take chat down permanently -- which would also
  remove the means to fix it.

Authorisation is inherited from authorizedMessage: only allowlisted
senders reach any handler, so /restart is admin-only by construction.
main.go supplies Reload, which re-reads config from disk and refreshes
token and allowlist; other fields still need a full daemon restart, since
they are wired at construction.
2026-07-27 05:21:58 +10:00
sam 9fd4696492 fix(telegram): publish command menu to all scopes, not just default
The menu still showed ~60 stale hermes commands (/steer, /reload_mcp,
/background) even though SetMyCommands succeeded and logged 8 commands.

Telegram resolves a chat's menu by scope specificity rather than by
recency: a list registered against all_private_chats wins over the
default scope in every DM. We wrote only the default scope, so hermes's
older per-scope registrations kept shadowing ours. getMyCommands confirms
it -- default held our 8, all_private_chats and all_group_chats each held
hermes's ~60.

That state lives on Telegram's side, keyed to the bot token, so it
survived the migration off hermes and would survive any redeploy. Publish
to default, all_private_chats and all_group_chats so the leftovers are
overwritten rather than shadowing us. One failing scope no longer aborts
the rest.
2026-07-27 05:18:26 +10:00
sam cb147b7a37 feat(telegram): deny-by-default sender allowlist + command menu (16.33, 16.34)
Allowlist (16.33). telegram.New was called with a nil allowlist and
isChatAllowed returned true whenever the list was empty, so any Telegram
user who found the bot could talk to it; AllowedChatIDs was not plumbed
into config, so there was no way to close it. Chat tools run with the
daemon's own authority, so this had to be fixed before wiring any real
tools to the chat agent.

Now chat.telegram.allowed_user_ids configures it and an empty list denies
everyone: a bot handle is public, so failing open is not a safe default.
The check matches the sender (from.id) rather than the chat, so adding
the bot to a group cannot be used to inherit access. Rejections log the
sender id and answer once, so a legitimate user missing from the list can
tell the bot is misconfigured rather than dead. Startup warns when the
gateway is enabled with an empty list.

The previous TestIsChatAllowed asserted 'empty allowlist allows all' --
it encoded the vulnerability -- and is replaced by fail-closed tests.

Command menu (16.34). SetMyCommands was never called, so Telegram showed
no menu and the commands Router implements were undiscoverable; asked
about /commands the LLM confidently answered it had none. The published
list mirrors what Router actually handles. Failure is logged, not fatal:
it costs discoverability, not function.
2026-07-27 05:14:34 +10:00
sam 285c618f74 fix(chat): drain FullStream, not TextStream — streaming deadlocked every reply
Streamed chat replies hung on the first token: the draft rendered an
empty cursor, the typing indicator never cleared, and the turn never
completed.

RouteStream consumed stream.TextStream, but ai-sdk's channel contract
makes FullStream authoritative and requires draining it until close --
its writes are synchronous, so an unread FullStream applies backpressure
and stalls the producer. Once its buffer filled, the producer blocked,
TextStream stopped yielding, and the range loop blocked forever.

TextStream was the wrong source regardless: it is explicitly best-effort
and drops deltas when not drained, so a reply reconstructed from it can
silently lose text. Range over FullStream and collect StreamPartTextDelta
parts, exactly as the SDK documents.

Also bumps ai-sdk v0.1.17 -> v0.1.18 (build, full suite and lint clean).
2026-07-27 05:04:04 +10:00
sam 3e3911a423 feat(telegram): native rich messages + streamed replies (16.32)
Upgrades go-telegram/bot v1.18.0 -> v1.22.0 and uses the Bot API's rich
message support instead of hand-rolled formatting.

The previous commit converted LLM Markdown into Telegram's HTML subset,
on the premise that the API could not take Markdown directly and had no
table element. Both are true of v1.18.0 but not of v1.22.0, which adds
sendRichMessage/sendRichMessageDraft taking InputRichMessage{Markdown},
plus RichBlockTableCell for native tables. markdownToHTML and its tests
are deleted: LLM Markdown, tables included, now goes to Telegram as-is.

Replies also stream. runtime.ChatStream already returned a TextStream
and sendRichMessageDraft renders partial output, so the only missing
piece was a gateway seam: gateway.LLMStreamResponder plus Router.
RouteStream, which degrades to the blocking Route when unset so any
adapter can call it unconditionally. Local commands answer from local
state and are not streamed; an unrecognised /command is, since Route
hands it to the LLM. main.go derives both responders from one shared
turn implementation.

Draft updates are throttled to one per 700ms to respect per-chat rate
limits, and every streaming/rich path falls back rather than dropping a
reply: a rejected rich send retries unformatted, and a failed draft
update is skipped since the final message is authoritative.
2026-07-27 04:57:36 +10:00
sam b52accf24a config: set containers.network explicitly for the docker deployment
Pins the agent-container network instead of relying on selfNetwork()
auto-detection, which silently fell back to the default bridge and broke
NATS resolution for spawned agents.
2026-07-27 04:51:10 +10:00
sam bf0e348cbb fix: pass HEYARCHIE_TELEGRAM_BOT_TOKEN through to archied
The telegram chat gateway is enabled via chat.telegram.token_env in
config.toml, but compose never forwarded the named variable, so
cfg.Chat.Telegram.TokenEnv resolved to empty and archied exited 1.
Same class of bug as ARCHIE_GITEA_TOKEN_ARCHIE.
2026-07-27 04:51:10 +10:00
sam cb1b0eb11a feat(telegram): typing indicator + Markdown rendering (part of 16.6)
Two gaps visible in the live heyarchie bot:

1. No typing indicator. A non-command message runs a full LLM turn
   (seconds), during which the chat looked dead. defaultHandler now
   shows the typing action for the duration, refreshed every 4s since
   Telegram clears it after ~5s.

2. ParseMode was never set, so LLM Markdown reached users verbatim:
   literal **bold**, backticks, and pipe tables. helpHandler was worse
   -- it emitted <b>Archie Gateway</b> with no ParseMode, so the raw
   tags were shown.

The SDK has no Markdown->Telegram converter (EscapeMarkdown does the
inverse: it escapes text so it renders literally), and neither native
parse mode helps, since Telegram's Markdown dialects use single-asterisk
*bold* whereas LLMs emit **bold**. So markdownToHTML converts to the
HTML subset Telegram accepts, mapping headings to <b>, bullets to '•',
and tables to <pre> (Telegram has no table element). Send falls back to
unformatted text if Telegram rejects the markup, so a conversion bug can
never swallow a reply.
2026-07-27 04:47:21 +10:00
sam 18948ac0e3 chore: remove accidentally-committed build/test scratch artifacts
.gotmp/ (Go build cache and test temp-dir output, created as a
workaround for a tmpfs disk-quota issue in this environment) got swept
into a prior commit by a broad `git add -A`. Remove it and gitignore
the directory so this doesn't recur.
2026-07-27 04:43:37 +10:00
sam 325aa7ae35 test message 2026-07-27 04:39:39 +10:00
sam 4c0fc12450 test message 2026-07-27 04:39:27 +10:00
sam 52015c81b0 fix: pass ARCHIE_GITEA_TOKEN_ARCHIE through to archied container
The archied service only forwarded ARCHIE_GITEA_TOKEN, but config.toml
names ARCHIE_GITEA_TOKEN_ARCHIE for the archie identity. Recreating the
container via docker compose (rather than a manual docker run with an
explicit -e) silently dropped the token.
2026-07-27 04:31:43 +10:00
sam 38a746a891 fix: make agent-container Docker network explicitly configurable
archied's container-mode agent tasks were all failing with "nats: no
responders available for request" in production. Root cause: pool.go's
selfNetwork() auto-detects the daemon's own Docker network by looking up
a container named after os.Hostname(), then joins spawned agent
containers to that same network so they can resolve "nats" by name.
On carina this detection was silently failing (wrong/stale hostname vs.
actual container ID) and returning "", so every per-task agent container
landed on the default bridge network instead — unable to resolve "nats",
never subscribing, hence "no responders" on every request.

selfNetwork() swallowed every failure silently (only logged on success),
so this had no diagnostic trail.

Fix: added Containers.Network config field (containers.network in
config.toml) so deployments can name the network explicitly instead of
relying on fragile self-detection; selfNetwork() remains as a fallback
but now logs a warning on every failure path so this doesn't silently
recur. Wired through container.Config and cmd/archied/main.go.
2026-07-27 04:25:28 +10:00
sam 63719cc3ec fix: restore [forge] token_env backward compat, fixing prod crash-loop
Both archied production containers (archie-core-archied-1 and -winter-1)
were crash-looping on carina with "forge token (engine \"env\", key
\"ARCHIE_GITHUB_TOKEN\") is required" despite being configured for gitea.

Root cause: the secrets-engine migration replaced [forge]'s flat
token_env string field with a {engine, key} struct (Forge.Token), but
dropped the old field entirely instead of keeping it as a deprecated
fallback like NATSConfig and TelegramConfig already do. TOML silently
ignores unknown keys, so deployed configs still using token_env had
their token config dropped without any warning, and finalize()
defaulted to demanding ARCHIE_GITHUB_TOKEN.

Fix: re-added Forge.TokenEnv and honor it in finalize() when the new
Token struct is unset, matching the existing NATS/Telegram pattern.
New-style [forge.token] still wins if both are present. Added
regression tests for both cases.

Operationally also fixed the two live configs on carina
(~/.config/archie/config.toml, winter.toml) to the new schema, and
added missing work_dir/db_path to winter.toml (its container had no
config-overlay, so it was defaulting to /root/.local/share/archie
instead of the mounted volume). Both containers verified healthy and
processing real issues after restart.
2026-07-27 04:13:04 +10:00
sam b9ecf37a48 refactor: replace fmt.Sprintf with fmt.Appendf in test 2026-07-27 04:03:23 +10:00
sam 80cd473559 fix: remove local filesystem replace directive for NellDB
go.mod pointed NellDB at a local dev-machine path
(/work/apps/nell-engine) instead of the published v0.2.5 module,
which the Gitea CI runner can't resolve — every push since the
replace was added has failed the deploy workflow's docker build
(go mod download: no such file or directory), silently leaving
carina on a two-day-old image. Confirmed nell-engine's local HEAD
is functionally identical to the already-tagged-and-pushed v0.2.5
(only a trivial .gitignore commit ahead), so dropping the replace
and re-resolving from the registry is a no-op for behavior.
2026-07-27 04:00:51 +10:00
sam 6fe1a7d037 fix: lint cleanup across repo (errcheck, staticcheck, ineffassign, unused)
- daemon.go: real bug — maybeRetryParked resolved fg := d.forgeFor(task)
  (matching markDead's pattern) but called d.Forge.SetStateLabel instead
  of fg.SetStateLabel, silently using the wrong forge client for
  multi-identity/multi-forge task routing. Fixed to use fg throughout.
- telegram.go: updateThreadID existed but was never called anywhere;
  wired it into updateLoggingMiddleware so debug logs include thread_id.
- Two SA9003 empty-branch tests (nell adapter_test.go, tools
  toolentry_test.go) were dead assertions with no body; implemented the
  actual check instead of deleting them.
- memory manager_test.go: mockProvider.lastConfigSchema/lastBackupPaths
  were declared but never recorded; wired GetConfigSchema/BackupPaths to
  populate them and strengthened the aggregation tests to assert on
  per-provider content, not just counts.
- Removed genuinely dead gateway messageevent_test.go helpers (intPtr/
  i64Ptr, marked //go:fix inline, already fully superseded by the new()
  builtin used throughout the file).
- Remaining errcheck findings (defer Close/Flush/Write, os.Setenv, etc.
  in test files) fixed with the existing `_ = ` convention already used
  elsewhere in the codebase.

go build ./..., go test ./... (all packages ok), and
golangci-lint run ./... all clean.
2026-07-27 03:49:33 +10:00
sam 64352a06f3 beads: sync export after commit 2026-07-27 03:46:56 +10:00
sam 97e6a54da5 fix: MCP stdio transport lifecycle races and dead SendTimeout config
Implement the SendTimeout config field (previously silently ignored) via a
timeout-bounded write helper, and close two related races found during
adversarial review: Start()/Stop() could interleave across separate lock
acquisitions, and a subprocess spawned by a fresh Start() or a
crash-triggered restart could clobber a StateStopped already committed and
reported by a concurrent Stop(). Both spawn-commit paths now funnel through
a single guarded commitSpawnedProcess. Closes archie-core-abg.17.16,
archie-core-abg.17.23, archie-core-abg.17.41.
2026-07-27 03:46:47 +10:00
sam d227330243 beads: sync export after commit 2026-07-27 03:34:53 +10:00
sam f73b2d1c8c feat: memory manager sync/prefetch/scan/shutdown + broad in-flight epic work
Checkpoint commit covering concurrent work across several archie-core-abg
epics to avoid losing in-progress state:

- Memory manager (18.7-18.16): background sync pipeline, prefetch with
  timeout, memory-write notification, threat scanning, shutdown drain
  with abandoned-write tracking, frozen snapshot pattern. Wired
  ScanContent and NotifyMemoryToolWrite into HandleToolCall so scanning
  and notification actually apply to writes, not just exist as unused
  primitives.
- Fixed a literal unresolved merge-conflict that had been committed to
  internal/memory/scrubber/scrubber.go.
- Tool provider/registry, MCP client/transport (stdio, HTTP, SSE),
  multimodal results, disclosure.
- Pairing device auth store, rate limiting.
- Gateway compression, session store, tasks.
- Various workflow, plugin host, and agentexec updates.
2026-07-27 03:34:46 +10:00
sam 2b1045c0ad feat: secrets-engine registry with yaegi extension interface (archie-core-xec)
Adds internal/secret: a pluggable Engine interface (Name/Version/Resolve)
resolved through a Registry, so secrets backends (sops, Bitwarden Secrets
Manager, Vault/OpenBao) aren't hard-coded into the binary. Only the "env"
engine is compiled in; custom engines are Yaegi-interpreted .go plugins
loaded via Registry.LoadDir, mirroring internal/plugin's conventions
(secretextract provides the generated, nil-guarded symbol table for the
Yaegi/Go interface boundary).

config.Forge.TokenEnv is replaced end-to-end with config.Forge.Token
(secret.SecretRef{Engine, Key}) -- finalize() defaulting, forge token
resolution in cmd/archied/main.go, and per-identity validation that now
requires an explicit token instead of silently resolving to "". No
backwards-compat shim.

Provider.APIKeyEnv, NATSConfig.TokenEnv, and TelegramConfig.TokenEnv are
deliberately not migrated here -- they're forwarded by name to
ai-sdk/runtime and subprocess workers rather than resolved centrally,
which needs its own eager-resolve-then-inject design pass
(archie-core-xec.4). The three shipped engine plugins (sops, bws,
vault/openbao) are tracked separately as archie-core-xec.1-3.

Adversarially reviewed by a fresh agent with no implementation context;
fixed the two findings that survived (missing per-identity token
validation, underdocumented nil-wrapper Resolve edge case).
2026-07-26 14:49:32 +10:00
sam 146acf5466 feat: secret engine registry foundation (archie-core-xec)
internal/secret package:
- Engine interface (Name, Version, Resolve) for pluggable secret backends
- SecretRef type replacing TokenEnv/APIKeyEnv string fields
- ResolveOrEnv for backward-compatible env-var fallback
- Built-in env engine registered by default
- Registry with Register/Get/Resolve/LoadDir (yaegi-based)
- DefaultRegistry() singleton for one-off resolution
- 12 tests, race-clean

Scoped to foundation only. Provider/NATS/Telegram migration deferred
to xec.4 (separate bead — those call sites forward env var names to
subprocesses/runtimes and need eager-resolve-then-inject, not a simple
field rename).

40/40 packages pass with -race.
2026-07-26 14:20:19 +10:00
sam b95993c44a fix: address adversarial review findings (21v + 19v)
Session persistence (21v):
- Mutex coverage on all nellSessionStore read operations
- Router.Store nil guard in handleStatus()

Config (19v):
- Remove dead code no-op in finalize() (Label='' assignment)
- Nil guard on loadFeatureFile() cfg parameter

40/40 packages pass with -race.
2026-07-26 13:56:25 +10:00
sam f4787a819d feat: email channel + Channel interface with config schema validation
Email channel (internal/channels/email):
- SMTP server receiving inbound emails on configurable port
- Multipart body extraction (text/plain from MIME)
- SMTP relay for outbound replies with STARTTLS + AUTH
- 8 tests, race-clean

Channel interface (internal/channels/channel.go):
- ConfigSchema() — JSON Schema for channel configuration
- ValidateConfig() — validates channel-specific config at startup
- All three channels (Telegram, Email, Webhook) implement it
- Compile-time guard: var _ channels.Channel = (*Gateway)(nil)

Config: ChatConfig.Email added (listen_addr, relay_addr).
Daemon: email gateway wired into main.go behind chat.email block.

40 packages pass with -race.
2026-07-26 13:36:56 +10:00
sam 20a1210d0e feat: webhook platform + persona registry (items 5+6)
Webhook platform (internal/channels/webhook):
- Gateway adapter with HTTP server, HMAC validation, dot-notation template extraction
- Per-route configuration with secret-based signing
- Deliver-to-origin mode for sync responses
- 11 tests, race-clean

Persona registry (internal/gateway/persona.go):
- PersonaRegistry with per-session active persona selection
- DefaultPersonas(): helpful, concise, technical, creative, teacher
- Persona prompt prepended to system prompt in LLMResponder
- Thread-safe, 5 tests

Config: ChatConfig.WebhookAddr added for webhook listen address.
All 39 packages pass with -race.

Closes abg.5.3, abg.34.
2026-07-26 10:39:58 +10:00
sam b261ee4b91 feat: context compression for long-running sessions
CompressionConfig with threshold-based triggering (default 50% of 128k window).
Protects first 3 and last 20 messages. Truncated middle replaced with statistical
summary (turns, tokens removed, topic range). CompressHistory() returns
CompressedView with before/after token counts. Integrated into Telegram
LLMResponder — fetches 100-message window, compresses before LLM call.

Matches Hermes config: threshold=0.5, protect_first=3, protect_last=20.
All 38 packages pass with -race.

Closes abg.33.
2026-07-26 10:36:24 +10:00
sam 8d4f4eb89d feat: verify Telegram topic thread support — already functional
ThreadID flows end-to-end: Telegram update → gateway.Message →
sessionKey() → NellDB session store → reply routing. Added
updateThreadID() helper for middleware logging. All 38 pass.
2026-07-26 10:34:26 +10:00
sam 948efde036 feat: session persistence — message storage, history retrieval, search
SessionStore extended with SaveMessage, RecentMessages, SearchMessages.
NellDB-backed implementation uses a separate DocDB collection for messages
keyed by session:seq. Conversation history loaded into LLM context for each
Telegram message. Responses persisted. Substring search fallback (vector
search deferred to memory provider embedding integration).

Adapter.Store() exported to share the underlying NellDB engine for session
collections without opening a second log.

Telegram LLMResponder now:
- Saves inbound messages to session store
- Loads 20 most recent messages as chat.Message history
- Sends full conversation context to llm.Chat()
- Persists the assistant response

All 38 packages pass with -race.
2026-07-26 10:33:13 +10:00
sam 1d76560911 feat: wire Telegram LLM routing — non-command messages routed to AI
LLMResponder adapter wraps llm.Chat() with model from cfg.Models[chat] (falls
back to builder). Gateway-local commands (/status, /models, /model, /spawn)
still handled directly. LLM created before gateway so it's available at
router construction time. All 38 packages pass.
2026-07-26 10:29:07 +10:00
sam 0314955587 feat: wire memory, guardrails, and tool registry into daemon agent loop
Memory:
- MemoryManager created in main.go with built-in file-backed provider
- SystemPromptBlock() injected into every agent stage request via ExtraRules
- memoryPrompt() helper on Daemon, threaded through TaskContext.SystemPrompt

Guardrails:
- GuardrailEngine created from DefaultGuardrailConfig in main.go
- RecordSuccess/RecordFailure called after every agent stage run
- Threaded through TaskContext.Guardrails for per-task guardrail enforcement

Tool registry:
- NewRegistry() created at startup, MCP servers started from config
- Passed to Daemon.ToolRegistry for dynamic tool discovery

Daemon changes:
- Memory, Guardrails, ToolRegistry fields added (nil-safe, backward compat)
- TaskContext gains SystemPrompt + Guardrails fields
- Agent stage injects memory context into ExtraRules
- Agent stage records guardrail state after each run

Telegram LLM routing deferred (TODO comment) — gateway commands work.
All 38 packages pass with -race.
2026-07-26 10:25:07 +10:00
sam e8f78dd0d5 test: regression tests for all audit gaps — 6 enhanced + 4 new packages
Telegram: splitLongMessage (8 cases), isChatAllowed, updateMetadata (4 cases),
  panicRecoveryMiddleware, updateLoggingMiddleware, authorizedMessage, stop-while-stopped
Container: error paths, payload round-trip, overwrite, minimal payload
Events: buffer defaults, subscribe-after-close, double-close safety,
  slow-subscriber isolation, multi-subscriber ordering, publish timestamping
NATS RPC: envelope edge cases, JSON round-trip, request timeout, rollback
NellDB: empty store (6 ops), concurrent enqueue/claim (20 goroutines),
  context cancellation, oversized payload clipping, unmarshalable data,
  status transitions, events ordering, recover stale, clear terminal
Gateway tasks: empty/long title, idempotent enqueue, chat label

New packages with tests (formerly zero-test):
  internal/gate (220 lines), internal/gate/gateextract,
  internal/plugin/pluginextract, internal/workflow/wfextract

All 37 packages pass. Fixes regression gaps from audit.
2026-07-26 10:05:44 +10:00
sam 8356863712 feat: Tools P1 — guardrails, classification, budget, availability, disclosure, dispatch
- ToolCallGuardrailConfig + GuardrailEngine with RecordSuccess/RecordFailure
- ToolClassification bitmask (idempotent/mutating) with dispatch gating
- TurnBudget for token/char accounting with spill-to-disk
- AvailabilityCache with TTL + failure grace window
- Progressive disclosure engine for tool schema filtering
- Tool dispatch executor with parallel/serial classification
- RecordSuccess fix: now returns GuardrailDecision (no-progress threshold)
- All tests pass with -race, 58 new test functions across 6 test files
2026-07-26 09:53:38 +10:00
sam f6d51416f0 chore: replace 607 em-dashes with double hyphens project-wide
Includes MCP crash-after-init test fix (crash moved from handle() to serve()
entry point so transport sees immediate subprocess death).
2026-07-26 09:53:33 +10:00
sam 16d6cd62b7 feat: memory manager sync pipeline, prefetch, notify, threat scan, shutdown drain (18.7-18.16)
sync.go — background serialized writer (single goroutine) for async
memory writes. Prefetch with 8s timeout per provider.

scanner.go — threat pattern scanning for memory content.
ThreatBlock error type for rejecting dangerous writes.

manager.go — HandleToolCall routes through Manager (not provider
directly), scanning content/replacement args before dispatch and
notifying external providers post-write. Shutdown drain with 5s
timeout and abandoned-write tracking.

4 tests added covering scan-notify flow. go test -race, gofmt,
go vet, build all clean on internal/memory.

16 beads closed: 18.7-18.9, 18.14-18.16 (impl) + 18.27-18.32 (verify)
2026-07-26 09:23:05 +10:00
sam 52cc8f8a14 feat: memory P1 — sync pipeline, prefetch, notify, frozen snapshot, threat scanning, shutdown drain (18.7-18.9, 18.14-18.16)
sync.go — background serialized writer (single goroutine) for async
memory writes. Prefetch with 8s timeout per provider.

scanner.go — threat pattern scanning for memory content.

manager.go — notify_memory_tool_write bridging built-in writes to
external providers. Shutdown drain with 5s timeout.

All 6 impl + 6 verify beads closed. Memory epic complete.
2026-07-26 09:22:12 +10:00
sam 628b44387a beads: sync after memory scrubber + schema + builtin tool 2026-07-26 08:58:27 +10:00
sam 942deb9336 feat: built-in file-backed memory tool (18.12, 18.13)
internal/memory/builtin/provider.go — MemoryProvider backed by
MEMORY.md + USER.md files. LLM-callable memory tool with
add/replace/remove actions using section-sign delimited entries
and substring matching.

internal/memory/builtin/store.go — file read/write with atomic
replace and chmod 0600.
2026-07-26 08:58:27 +10:00
sam e8fe1b12a7 feat: tool schema normalization for memory providers (18.11)
internal/memory/schema.go — normalizes memory-provider-exported
tool schemas between bare and wrapped OpenAI formats. Handles
both function-call wrapper objects and bare name+description+params
shapes. Converges to a consistent internal representation.
2026-07-26 08:58:26 +10:00
sam 9d1a190908 chore: close memory provider verification issues 2026-07-26 02:27:06 +10:00
sam bff3c40ca9 merge: integrate memory infrastructure features (StreamingContextScrubber, schema normalization, built-in store, memory edit actions)
Resolve conflict in `.beads/` tracking files and scrubber implementation:
- Accept 8642f40's full implementation of StreamingContextScrubber with io.Writer interface, partial chunk boundary handling, nested tags, zero-alloc fast path, and comprehensive tests.
- Take incoming changes for issues tracking: close multiple verification tasks (18.10–18.13, 18.23–18.26) after adversarial review, update status for in-progress tasks (18.17, 18.18).
2026-07-26 02:26:25 +10:00
sam e5627930eb Merge pull request 'feat: StreamingContextScrubber for memory-context fence stripping (18.10)' (#77) from worktree-stateful-meandering-cloud into main
Reviewed-on: sam/archie-core#77
2026-07-25 16:15:41 +00:00
sam d48953d9e7 fix: Flush() leaking in-block content when stream ends mid-close-tag
Pending bytes buffered while inside a <memory> block were unconditionally
emitted as literal text by Flush, leaking hidden memory-context content
into visible streamed output when a stream cut off mid-tag (e.g. "...secret</mem").
Track pendingInBlock at capture time so Flush discards in-block pending
bytes instead of emitting them. Also corrects stale doc comments claiming
underlying writer errors are surfaced (they're intentionally discarded).

Found by adversarial review of 18.10.
2026-07-26 02:11:28 +10:00
sam 886591f674 feat: StreamingContextScrubber for memory-context fence stripping (18.10)
Stateful io.Writer that strips <memory>...</memory> fences from
streaming output, handling partial chunks split across tag
boundaries, nested tags, and missing closing tags.
2026-07-26 02:08:10 +10:00
sam f0c2a3eda5 beads: sync memory verification fixes + beads state 2026-07-26 01:57:41 +10:00
sam 0746950cb7 fix: MCP transport framing + crash retry + test harness (17.16)
framing.go: documented that readMessage caller must manage the
bufio.Reader lifetime. Creating a new bufio.Reader per call silently
drops buffered data and breaks multi-message streams.

transport.go: added crashCount check alongside startupFailures for
the MaxRetries limit — crash-looping subprocesses (spawn succeeds
but process immediately dies) now count toward the retry cap.

transport_test.go: replaced os.Exit(1) with syscall.Exit(1) in
crash-after-init behavior — Go's test harness intercepts os.Exit
and panics instead of exiting, keeping the process and its pipes
alive indefinitely. Replaced os.Exit(0) with runtime.Goexit() in
TestMCPServerHelper for clean goroutine exit.

Framing multiple-message test passes. Crash retry tests may need
further debugging in the transport spawn/reader lifecycle.
2026-07-26 01:57:41 +10:00
sam 3b9c280b12 wip: MCP transport types + framing + tests (17.16 partial)
Deepseek workflow ran before hitting session limit. Delivered:
  types.go — TransportState enum, JSON-RPC 2.0 Request/Response/Error
  framing.go — Content-Length header framing (LSP-compatible, 4MB max)
  transport_test.go — 585 lines of tests (red: implementation missing)

Memory verification fixes also included (lifecycle, manager, test updates).

transport.go still needed — the main MCPServer Connect/Disconnect
implementation. Tests are written, implementation is ~200 lines.
2026-07-26 01:40:05 +10:00
sam 156453cf74 fix: tool registry — 8 bugs from adversarial review (17.1, 17.2)
Verification review found 8 bugs, all fixed with regression tests:
  - Available() deadlock: CheckFn evaluated outside RLock
  - Register() shared references: Clone() defensive copy before storage
  - Clone() shallow nested schemas: deepCopyAny for maps/arrays
  - stringLit: no backtick/escape handling → strconv.Unquote
  - intLit: no negative/hex/octal/binary → strconv.ParseInt
  - Discover: abort on first error → Continue + errors.Join
  - isRegisterCall: too broad → only DefaultRegistry() calls match
  - schemaLit: only string values → handle ints, bools, nested maps

38 tests pass. All 34 packages green. golangci-lint + gofmt clean.

Closes: archie-core-abg.17.1, 17.2
2026-07-26 01:31:17 +10:00
sam bc1caf67aa feat: BasePlatformAdapter interface + Session types (16.3, 16.5, 16.9, 16.10, 16.11)
adapter.go — SendResult struct (success, message_id, error, retryable,
retry_after, continuation_message_ids, error_kind), ChatInfo struct
(name, type, chat_id, thread_id), BasePlatformAdapter interface
(Connect, Disconnect, Send, ChatInfo).

session.go — SessionSource (platform, chat_id/name/type, user_id/name,
thread_id, guild_id, scope_id, profile, is_bot, metadata) with Key()
for deterministic session key. SessionContext wrapping source with
connected_platforms, home_channels, session_key/id, timestamps.

session_store.go — SessionStore interface (GetOrCreate, Get, Reset,
List, GetByChannel, Touch, Delete, Close) + nellSessionStore backed
by nell.DocDB with mutex-guarded Save/Delete for race safety.

Verification: 4 findings fixed (gofmt alignment, race on mutex,
!= true anti-pattern, missing zero-value assertions). 58 tests pass
(incl -race), go vet + gofmt + golangci-lint clean.

Closes: archie-core-abg.16.3, 16.5, 16.9, 16.10, 16.11
2026-07-26 01:29:36 +10:00
sam 30b76f2ead feat: MessageType enum + MessageEvent struct (16.1, 16.2)
internal/gateway/messagetype.go — 14-value MessageType enum with
IsMedia(), IsRich(), IsEphemeral() classification helpers.

internal/gateway/messageevent.go — platform-neutral MessageEvent:
text, type, media attachments (file metadata, dimensions, duration),
reply context (message ID, text, author), editing support (edited
flag, edit timestamp), capability flags (streaming, code blocks).

Verification agent found 7 issues, 5 fixed (pointer types for
FileSize/Width/Height/Duration, MsgSticker in IsMedia, IsRich
coverage, ToLegacy edge cases), 2 correctly deferred.

42 tests pass. Build + vet + fmt clean.

Closes: archie-core-abg.16.1, archie-core-abg.16.2
2026-07-26 01:19:38 +10:00